Please see phrase_table.ipynb for phrase-based translation using a Mandarin GPT.

Cantonese-Mandarin phrase table: https://github.com/bluebat/msgchi/blob/master/cmn2yue.dic

Common traditional characters: https://github.com/kaienfr/Font/blob/master/learnfiles/chinese%E7%AE%80%E7%B9%81%E5%B8%B8%E7%94%A8%E5%AD%97%E8%A1%A8.txt

Common Cantonese words: https://github.com/rime/rime-pinyin-simp/blob/master/pinyin_simp.dict.yaml

Common Mandarin words: https://github.com/liangqi/chinese-frequency-word-list/blob/master/xiandaihaiyuchangyongcibiao.txt

pip install google-cloud-translate==2.0.1

export GOOGLE_APPLICATION_CREDENTIALS=translate-english-to-mandarin-c793a8415d64.json